How Experian and Resistant AI Tackle Financial Crime

Experian has expanded its threat detection capabilities through Transaction Forensics, an AI-powered platform built to identify complex financial crime patterns in real time.

The system is the first major collaborative output since Experian's July 2025 strategic investment in Resistant AI and demonstrates a wider industry movement toward layered, intelligence-led threat detection architectures.

Transaction Forensics targets UK financial institutions and merges Experian's consumer and commercial datasets with Resistant AI's behavioural and transaction analytics to deliver granular, real-time risk assessment across bank-to-bank payment channels.

AI models for transaction monitoring

The platform deploys more than 80 AI models to evaluate transaction intent as payments occur.

Payment signals are enriched with identity, credit, fraud and anti-money laundering data alongside historical behavioural insights.

This approach is designed to detect threats that traditional rule-based monitoring systems increasingly fail to catch.

Financial institutions are dealing with a rise in AI-enabled fraud, from sophisticated authorised push payment scams to coordinated mule networks.

These attacks operate at speeds and scales that legacy systems cannot match, creating what security teams refer to as the detection gap.

Paul Weathersby, Chief Product Officer for Experian UK&I, says: "Transaction Forensics marks a major step forward in fraud and financial crime prevention, one which is only possible thanks to our leading innovation and trusted, high-quality data."

Challenges in tightening detection controls

Efforts to strengthen detection controls often create friction.

Higher false positive rates can frustrate legitimate users and increase operational costs, as fraud teams manually review growing volumes of flagged transactions.

Regulatory scrutiny is also increasing.

According to the Financial Conduct Authority, explainable AI and alignment with Consumer Duty outcomes are now key compliance requirements.

Transaction Forensics is a response to these operational and regulatory pressures.

Layered security architecture approach

Rather than replacing existing monitoring infrastructure, the system functions as an additional analytical layer.

Institutions can enhance detection capabilities without overhauling core systems.

It can be deployed across Faster Payments, BACS and CHAPS, or selectively applied to high-risk transaction flows.

According to pilot testing, the platform delivered a 200% increase in authorised push payment fraud detection, alongside an 80% reduction in false positives and a 50% decrease in total alert volumes. This could mean more accurate threat identification and sharper focus for investigation teams.

Martin Rehak, CEO of Resistant AI, says: "The use of AI in fraud and financial crime prevention is no longer optional but essential.

"By combining Resistant AI's advanced models with Experian's leading datasets, we are enabling financial institutions not just to address current attacks including APP fraud and money laundering but any new threats which will undoubtedly emerge in the years ahead."

Paul continues: "Financial services are facing a significant challenge in identifying and stopping fraud and financial crime attacks, which are increasingly enabled by AI and at a scale not seen before.

"Transaction Forensics harnesses the power of AI to help businesses meet that challenge head on."

Collaborative threat intelligence models

Financial crime has become more complex and technology-driven, making isolated defence strategies insufficient.

Partnerships are emerging as a critical strategy for institutions and technology providers looking to stay ahead of evolving threats.

The collaboration between Experian and Resistant AI exemplifies this strategic approach.

By combining complementary strengths, deep data assets on one side and advanced AI modelling on the other, the partnership could enable a more holistic approach to threat detection.

This is particularly relevant where risk signals are fragmented across identity, behaviour and transaction data.

Beyond technical capability, partnerships are also accelerating innovation cycles.

These joint developments allow organisations to respond more quickly to emerging fraud typologies, regulatory expectations and customer demands for seamless digital experiences.